Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network - Archive ouverte HAL Access content directly
Conference Papers Year : 2006

Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network

(1) , (1)
1

Abstract

Different problems of generalization of outlier rejection exist depending of the context. In this study we firstly define three different problems depending of the outlier availability during the learning phase of the classifier. Then we propose different solutions to reject outliers with two main strategies: add a rejection class to the classifier or delimit its knowledge to better reject what it has not learned. These solutions are compared with ROC curves to recognize handwritten digits and reject handwritten characters. We show that delimiting knowledge of the classifier is important and that using only a partial subset of outliers do not perform a good reject option.
Fichier principal
Vignette du fichier
cr1063195986091.pdf (146.22 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00104310 , version 1 (06-10-2006)

Identifiers

  • HAL Id : inria-00104310 , version 1

Cite

Harold Mouchère, Eric Anquetil. Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France). ⟨inria-00104310⟩
118 View
95 Download

Share

Gmail Facebook Twitter LinkedIn More